Question-Answering System

This repository contains the code and resources for a cutting-edge Question-Answering (QA) System that leverages the power of Knowledge Graphs and Language Models to optimize performance and accuracy. The system was designed and implemented to address the challenges in effectively answering questions and providing accurate information.

Project Description

The primary objective of this project was to develop a robust QA system that integrates Knowledge Graphs and Language Models. The project involved the following key tasks:

1. Implementation of Knowledge Graphs: The project involved the creation of a Knowledge Graph, which is a structured representation of information. The Knowledge Graph was designed to capture relationships between entities and provide a rich source of information for the QA system.

2. Implementation of Language Models: Cutting-edge Language Models were utilized to understand and generate human-like text. These models were trained on vast amounts of textual data and have the ability to process and comprehend natural language.

3. Comparative Analysis: A comparative analysis was conducted to evaluate the strengths and weaknesses of Knowledge Graphs and Language Models individually. The analysis aimed to understand the performance and limitations of each method in the context of a QA system.

4. Integration: The project aimed to effectively integrate Knowledge Graphs and Language Models to leverage their respective strengths and improve overall efficiency. The integration process involved developing strategies to combine the two methods seamlessly and produce more accurate and reliable answers.

Repository Structure

The repository is structured as follows:

• notebooks/: This directory contains the Colab notebooks with the full implementation.
• papers/: This directory contains the achademic papers used for the State of the Art study.
• QASystem_Benitozzi_Pretell.pptx: This file contains a Power Point presentation of the project.
• README.md: This file, providing an overview of the project and instructions for using the repository.

Contributing

Contributions to this project are welcome. If you would like to contribute, please follow these steps:

1. Fork the repository on GitHub.

2. Create a new branch for your feature or bug fix.

3. Make the necessary changes in your branch.

4. Submit a pull request describing your changes and their purpose.

License

This project is licensed under the MIT License.